coradoc-markdown 1.0.0 → 1.0.3

data/lib/coradoc/markdown/transform/to_core_model.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-require 'coradoc/core_model'
+require 'coradoc'
 
 module Coradoc
   module Markdown
@@ -62,6 +62,8 @@ module Coradoc
               transform_extension(model)
             when Coradoc::Markdown::AttributeList
               transform_attribute_list(model)
+            when Coradoc::Markdown::Comment
+              Coradoc::CoreModel::CommentBlock.new(content: model.text.to_s)
             when Coradoc::Markdown::Text
               model.content.to_s
             when Array
@@ -75,18 +77,33 @@ module Coradoc
 
           def transform_document(doc)
             children = Array(doc.blocks).map { |block| transform(block) }
+            children = prepend_frontmatter(children, doc.frontmatter)
 
-            Coradoc::CoreModel::StructuralElement.new(
-              element_type: 'document',
+            Coradoc::CoreModel::DocumentElement.new(
               id: doc.id,
               title: extract_title(doc),
               children: children
             )
           end
 
+          # If the Markdown document had raw frontmatter text, parse it
+          # via Codec into a typed FrontmatterBlock and prepend it so
+          # it participates in the standard block pipeline. Codec is
+          # the single source of truth for YAML parsing (DRY/MECE).
+          #
+          # The block is prepended even when the YAML is malformed —
+          # Codec returns an empty FrontmatterBlock in that case, which
+          # preserves the signal "frontmatter was present but invalid"
+          # for downstream consumers.
+          def prepend_frontmatter(children, frontmatter_text)
+            return children if frontmatter_text.nil? || frontmatter_text.strip.empty?
+
+            block = Coradoc::CoreModel::FrontmatterBlock::Codec.from_yaml(frontmatter_text)
+            [block, *children]
+          end
+
           def transform_heading(heading)
-            Coradoc::CoreModel::StructuralElement.new(
-              element_type: 'section',
+            Coradoc::CoreModel::SectionElement.new(
               level: heading.level,
               title: extract_text(heading.text),
               children: []
@@ -96,15 +113,13 @@ module Coradoc
           def transform_paragraph(para)
             content = extract_text(para.text)
 
-            Coradoc::CoreModel::Block.new(
-              element_type: 'paragraph',
+            Coradoc::CoreModel::ParagraphBlock.new(
               content: content
             )
           end
 
           def transform_code_block(block)
             Coradoc::CoreModel::SourceBlock.new(
-              element_type: 'block',
               content: block.code.to_s,
               language: block.language
             )
@@ -112,16 +127,17 @@ module Coradoc
 
           def transform_blockquote(blockquote)
             Coradoc::CoreModel::QuoteBlock.new(
-              element_type: 'block',
               content: blockquote.content.to_s
             )
           end
 
           def transform_list(list)
             items = Array(list.items).map do |item|
+              nested = item.sublist ? transform_list(item.sublist) : nil
               Coradoc::CoreModel::ListItem.new(
                 content: extract_text(item.text),
-                marker: list.ordered ? '1.' : '*'
+                marker: list.ordered ? '1.' : '*',
+                nested_list: nested
               )
             end
 
@@ -149,7 +165,7 @@ module Coradoc
               cells = if row.is_a?(Array)
                         row.map { |c| Coradoc::CoreModel::TableCell.new(content: c.to_s, header: false) }
                       else
-                        [Coradoc::CoreModel::TableCell.new(content: row.to_s, header: false)]
+                        row.to_s.split(' | ').map { |c| Coradoc::CoreModel::TableCell.new(content: c.to_s, header: false) }
                       end
               rows << Coradoc::CoreModel::TableRow.new(cells: cells)
             end
@@ -165,25 +181,21 @@ module Coradoc
           end
 
           def transform_link(link)
-            Coradoc::CoreModel::InlineElement.new(
-              format_type: 'link',
+            Coradoc::CoreModel::LinkElement.new(
               target: link.url,
               content: extract_text(link.text)
             )
           end
 
           def transform_inline(inline, format_type)
-            Coradoc::CoreModel::InlineElement.new(
-              format_type: format_type,
+            klass = Coradoc::CoreModel::InlineElement.format_type_class(format_type)
+            klass.new(
               content: extract_text(inline.text)
             )
           end
 
           def transform_horizontal_rule(_rule)
-            Coradoc::CoreModel::Block.new(
-              element_type: 'block',
-              block_semantic_type: :horizontal_rule
-            )
+            Coradoc::CoreModel::HorizontalRuleBlock.new
           end
 
           def transform_definition_list(dl)
@@ -221,13 +233,11 @@ module Coradoc
 
           def transform_math(math)
             if math.inline?
-              Coradoc::CoreModel::InlineElement.new(
-                format_type: 'stem',
+              Coradoc::CoreModel::StemElement.new(
                 content: math.content.to_s
               )
             else
               Coradoc::CoreModel::PassBlock.new(
-                element_type: 'block',
                 content: math.content.to_s,
                 language: 'latexmath'
               )
@@ -239,19 +249,16 @@ module Coradoc
             when :toc
               Coradoc::CoreModel::Toc.new
             when :comment
-              Coradoc::CoreModel::Block.new(
-                element_type: 'comment',
+              Coradoc::CoreModel::CommentBlock.new(
                 content: ext.content.to_s
               )
             when :nomarkdown
               Coradoc::CoreModel::PassBlock.new(
-                element_type: 'block',
                 content: ext.content.to_s
               )
             else
               # Unknown extensions: preserve content as a generic block
-              Coradoc::CoreModel::Block.new(
-                element_type: 'paragraph',
+              Coradoc::CoreModel::ParagraphBlock.new(
                 content: ext.content.to_s
               )
             end
@@ -263,12 +270,11 @@ module Coradoc
             attr_list.classes.each do |cls|
               attrs << Coradoc::CoreModel::ElementAttribute.new(name: 'class', value: cls.to_s)
             end
-            attr_list.attributes.each do |k, v|
-              attrs << Coradoc::CoreModel::ElementAttribute.new(name: k.to_s, value: v.to_s)
+            attr_list.attributes.each do |nv|
+              attrs << Coradoc::CoreModel::ElementAttribute.new(name: nv.name, value: nv.value)
             end
 
             Coradoc::CoreModel::StructuralElement.new(
-              element_type: 'attribute_list',
               children: attrs
             )
           end

data/lib/coradoc/markdown/transformer.rb

@@ -240,8 +240,8 @@ module Coradoc
 
           # Check for known patterns and transform them
           if element.key?(:heading)
-            level = element[:heading].to_s.length
-            text = element[:text] ? element[:text].to_s.strip : ''
+            level = heading_level(element[:heading])
+            text = extract_text(element[:text]).strip
             heading = Heading.new(level: level, text: text)
             # Apply IAL if present
             apply_ial_to_element(heading, element[:ial]) if element.key?(:ial)
@@ -287,6 +287,15 @@ module Coradoc
           # Definition list
           return transform_definition_list(element[:dl]) if element.key?(:dl)
 
+          # Unordered list
+          return transform_list(element[:ul], ordered: false) if element.key?(:ul)
+
+          # Ordered list
+          return transform_list(element[:ol], ordered: true) if element.key?(:ol)
+
+          # Table
+          return transform_table(element) if element.key?(:table_header)
+
           # Footnote definition
           if element.key?(:fn_id)
             content = if element[:fn_content_continued]
@@ -310,6 +319,82 @@ module Coradoc
           nil
         end
 
+        # ATX heading: level is the count of leading '#' chars.
+        # Setext heading: level is 1 for '=' underline, 2 for '-' underline.
+        def heading_level(heading)
+          s = heading.to_s
+          return s.length if s.start_with?('#')
+          return 1 if s.start_with?('=')
+          return 2 if s.start_with?('-')
+
+          s.length
+        end
+
+        # Transform a list (ul/ol). Items arrive as `[{li: {p: {ln: "x"}}}, ...]`,
+        # as bare `{li: ...}` subtrees, or as an Array of mixed paragraph +
+        # nested-list nodes when the item has a sublist.
+        def transform_list(items, ordered:)
+          items = [items] unless items.is_a?(Array)
+          list_items = items.map do |node|
+            li = node.is_a?(Hash) ? node[:li] : node
+            transform_list_item(li)
+          end
+          List.new(ordered: ordered, items: list_items)
+        end
+
+        def transform_list_item(li)
+          nodes = normalize_list_item_nodes(li)
+          text_parts = []
+          sublist = nil
+          nodes.each do |n|
+            case n
+            when Hash
+              if n.key?(:p)
+                text_parts << extract_text_from_p(n[:p])
+              elsif n.key?(:ul)
+                sublist = transform_list(n[:ul], ordered: false)
+              elsif n.key?(:ol)
+                sublist = transform_list(n[:ol], ordered: true)
+              end
+            else
+              text_parts << n.to_s
+            end
+          end
+          item = ListItem.new(text: text_parts.join(' ').strip)
+          item.sublist = sublist if sublist
+          item
+        end
+
+        # Normalize the various shapes a list-item node can take:
+        #   Hash {p: ...}     -> [{p: ...}]
+        #   Hash {ul: ...}    -> [{ul: ...}]  (nested list, no text)
+        #   Array [...]       -> [...] (mixed paragraph + nested list nodes)
+        #   String / Slice    -> [s]
+        def normalize_list_item_nodes(li)
+          return li if li.is_a?(Array)
+          return [li] unless li.is_a?(Hash)
+          return [li] if li.key?(:p) || li.key?(:ul) || li.key?(:ol) || li.key?(:li)
+
+          [li]
+        end
+
+        # Transform a table. Header row, separator row, and body rows.
+        def transform_table(element)
+          headers = extract_row_cells(element.dig(:table_header, :row))
+          body_rows = Array(element[:table_body]).map do |body_node|
+            extract_row_cells(body_node[:table_body_row][:row]).join(' | ')
+          end
+          Table.new(headers: headers, rows: body_rows)
+        end
+
+        def extract_row_cells(row)
+          Array(row).map do |cell|
+            next cell.to_s.strip unless cell.is_a?(Hash)
+
+            cell[:cell].to_s.strip
+          end
+        end
+
         # Transform definition list
         def transform_definition_list(dl_content)
           # The parser outputs term and definition as separate items

data/lib/coradoc/markdown/version.rb

@@ -2,6 +2,6 @@
 
 module Coradoc
   module Markdown
-    VERSION = '1.0.0'
+    VERSION = '1.0.3'
   end
 end

data/lib/coradoc/markdown.rb

@@ -21,7 +21,9 @@
 require 'parslet'
 require 'lutaml/model'
 
+# Coradoc document transformation library.
 module Coradoc
+  # Markdown document model, parser, and serializer.
   module Markdown
     # Error classes
     autoload :Errors, 'coradoc/markdown/errors'
@@ -54,6 +56,20 @@ module Coradoc
     autoload :Extension, 'coradoc/markdown/model/extension'
     autoload :Strikethrough, 'coradoc/markdown/model/strikethrough'
     autoload :Highlight, 'coradoc/markdown/model/highlight'
+    autoload :Subscript, 'coradoc/markdown/model/subscript'
+    autoload :Superscript, 'coradoc/markdown/model/superscript'
+    autoload :Underline, 'coradoc/markdown/model/underline'
+    autoload :CrossReference, 'coradoc/markdown/model/cross_reference'
+    autoload :NamedValue, 'coradoc/markdown/model/named_value'
+    autoload :Comment, 'coradoc/markdown/model/comment'
+    autoload :Admonition, 'coradoc/markdown/model/admonition'
+    autoload :ExampleBlock, 'coradoc/markdown/model/example_block'
+    autoload :OpenBlock, 'coradoc/markdown/model/open_block'
+    autoload :Sidebar, 'coradoc/markdown/model/sidebar'
+    autoload :Verse, 'coradoc/markdown/model/verse'
+    autoload :Pass, 'coradoc/markdown/model/pass'
+    autoload :Literal, 'coradoc/markdown/model/literal'
+    autoload :HardLineBreak, 'coradoc/markdown/model/hard_line_break'
 
     # Serializer
     autoload :Serializer, 'coradoc/markdown/serializer'
@@ -78,29 +94,12 @@ module Coradoc
       autoload :ParsletExtras, 'coradoc/markdown/parser/parslet_extras'
       autoload :HTML_ENTITIES, 'coradoc/markdown/parser/html_entities'
       autoload :AstProcessor, 'coradoc/markdown/parser/ast_processor'
+      autoload :FrontmatterParser, 'coradoc/markdown/parser/frontmatter_parser'
     end
 
     # Shared parser utilities
     autoload :ParserUtil, 'coradoc/markdown/parser_util'
 
-    # Convenience accessors for kramdown extension models
-    class << self
-      # Access AttributeList class
-      def AttributeList
-        @AttributeList ||= const_get(:AttributeList)
-      end
-
-      # Access Math class
-      def Math
-        @Math ||= const_get(:Math)
-      end
-
-      # Access Extension class
-      def Extension
-        @Extension ||= const_get(:Extension)
-      end
-    end
-
     class << self
       # Parse Markdown content into a Document model
       #
@@ -108,8 +107,11 @@ module Coradoc
       # @param options [Hash] Parsing options
       # @return [Coradoc::Markdown::Document] The parsed document model
       def parse(content, _options = {})
-        ast = Parser::BlockParser.new.parse(content)
-        Transformer.transform_document(ast)
+        split = Parser::FrontmatterParser.call(content)
+        ast = Parser::BlockParser.new.parse(split.body)
+        doc = Transformer.transform_document(ast)
+        doc.frontmatter = split.frontmatter if split.frontmatter?
+        doc
       end
 
       # Parse raw AST (for debugging)
@@ -144,6 +146,7 @@ module Coradoc
       # @param options [Hash] Serialization options
       # @return [String] The Markdown output
       def serialize(document, options = {})
+        document = Transform::FromCoreModel.transform(document) if document.is_a?(Coradoc::CoreModel::Base)
         Serializer.serialize(document, options)
       end
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: coradoc-markdown
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 1.0.3
 platform: ruby
 authors:
 - Ribose Inc.
@@ -13,30 +13,30 @@ dependencies:
   name: coradoc
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '2.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '2.0'
 - !ruby/object:Gem::Dependency
   name: lutaml-model
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 0.8.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 0.8.0
 - !ruby/object:Gem::Dependency
   name: parslet
   requirement: !ruby/object:Gem::Requirement
@@ -106,19 +106,24 @@ files:
 - lib/coradoc/markdown.rb
 - lib/coradoc/markdown/errors.rb
 - lib/coradoc/markdown/model/abbreviation.rb
+- lib/coradoc/markdown/model/admonition.rb
 - lib/coradoc/markdown/model/attribute_list.rb
 - lib/coradoc/markdown/model/base.rb
 - lib/coradoc/markdown/model/blockquote.rb
 - lib/coradoc/markdown/model/code.rb
 - lib/coradoc/markdown/model/code_block.rb
+- lib/coradoc/markdown/model/comment.rb
+- lib/coradoc/markdown/model/cross_reference.rb
 - lib/coradoc/markdown/model/definition_item.rb
 - lib/coradoc/markdown/model/definition_list.rb
 - lib/coradoc/markdown/model/definition_term.rb
 - lib/coradoc/markdown/model/document.rb
 - lib/coradoc/markdown/model/emphasis.rb
+- lib/coradoc/markdown/model/example_block.rb
 - lib/coradoc/markdown/model/extension.rb
 - lib/coradoc/markdown/model/footnote.rb
 - lib/coradoc/markdown/model/footnote_reference.rb
+- lib/coradoc/markdown/model/hard_line_break.rb
 - lib/coradoc/markdown/model/heading.rb
 - lib/coradoc/markdown/model/highlight.rb
 - lib/coradoc/markdown/model/horizontal_rule.rb
@@ -126,22 +131,96 @@ files:
 - lib/coradoc/markdown/model/link.rb
 - lib/coradoc/markdown/model/list.rb
 - lib/coradoc/markdown/model/list_item.rb
+- lib/coradoc/markdown/model/literal.rb
 - lib/coradoc/markdown/model/math.rb
+- lib/coradoc/markdown/model/named_value.rb
+- lib/coradoc/markdown/model/open_block.rb
 - lib/coradoc/markdown/model/paragraph.rb
+- lib/coradoc/markdown/model/pass.rb
+- lib/coradoc/markdown/model/sidebar.rb
 - lib/coradoc/markdown/model/strikethrough.rb
 - lib/coradoc/markdown/model/strong.rb
+- lib/coradoc/markdown/model/subscript.rb
+- lib/coradoc/markdown/model/superscript.rb
 - lib/coradoc/markdown/model/table.rb
 - lib/coradoc/markdown/model/text.rb
+- lib/coradoc/markdown/model/underline.rb
+- lib/coradoc/markdown/model/verse.rb
 - lib/coradoc/markdown/parser.rb
 - lib/coradoc/markdown/parser/ast_processor.rb
 - lib/coradoc/markdown/parser/block_parser.rb
+- lib/coradoc/markdown/parser/frontmatter_parser.rb
 - lib/coradoc/markdown/parser/html_entities.rb
 - lib/coradoc/markdown/parser/inline_parser.rb
 - lib/coradoc/markdown/parser/parslet_extras.rb
 - lib/coradoc/markdown/parser_util.rb
 - lib/coradoc/markdown/serializer.rb
+- lib/coradoc/markdown/serializer/builder.rb
+- lib/coradoc/markdown/serializer/config.rb
+- lib/coradoc/markdown/serializer/context.rb
+- lib/coradoc/markdown/serializer/element_serializer.rb
+- lib/coradoc/markdown/serializer/flavor.rb
+- lib/coradoc/markdown/serializer/registrations.rb
+- lib/coradoc/markdown/serializer/registry.rb
+- lib/coradoc/markdown/serializer/runner.rb
+- lib/coradoc/markdown/serializer/serializers/abbreviation.rb
+- lib/coradoc/markdown/serializer/serializers/admonition.rb
+- lib/coradoc/markdown/serializer/serializers/attribute_list.rb
+- lib/coradoc/markdown/serializer/serializers/blockquote.rb
+- lib/coradoc/markdown/serializer/serializers/code.rb
+- lib/coradoc/markdown/serializer/serializers/code_block.rb
+- lib/coradoc/markdown/serializer/serializers/comment.rb
+- lib/coradoc/markdown/serializer/serializers/cross_reference.rb
+- lib/coradoc/markdown/serializer/serializers/definition_list.rb
+- lib/coradoc/markdown/serializer/serializers/document.rb
+- lib/coradoc/markdown/serializer/serializers/emphasis.rb
+- lib/coradoc/markdown/serializer/serializers/example_block.rb
+- lib/coradoc/markdown/serializer/serializers/extension.rb
+- lib/coradoc/markdown/serializer/serializers/footnote.rb
+- lib/coradoc/markdown/serializer/serializers/footnote_reference.rb
+- lib/coradoc/markdown/serializer/serializers/hard_line_break.rb
+- lib/coradoc/markdown/serializer/serializers/heading.rb
+- lib/coradoc/markdown/serializer/serializers/highlight.rb
+- lib/coradoc/markdown/serializer/serializers/horizontal_rule.rb
+- lib/coradoc/markdown/serializer/serializers/image.rb
+- lib/coradoc/markdown/serializer/serializers/link.rb
+- lib/coradoc/markdown/serializer/serializers/list.rb
+- lib/coradoc/markdown/serializer/serializers/literal.rb
+- lib/coradoc/markdown/serializer/serializers/math.rb
+- lib/coradoc/markdown/serializer/serializers/open_block.rb
+- lib/coradoc/markdown/serializer/serializers/paragraph.rb
+- lib/coradoc/markdown/serializer/serializers/pass.rb
+- lib/coradoc/markdown/serializer/serializers/sidebar.rb
+- lib/coradoc/markdown/serializer/serializers/strikethrough.rb
+- lib/coradoc/markdown/serializer/serializers/strong.rb
+- lib/coradoc/markdown/serializer/serializers/subscript.rb
+- lib/coradoc/markdown/serializer/serializers/superscript.rb
+- lib/coradoc/markdown/serializer/serializers/table.rb
+- lib/coradoc/markdown/serializer/serializers/underline.rb
+- lib/coradoc/markdown/serializer/serializers/verse.rb
+- lib/coradoc/markdown/serializer/strategies/admonition/base.rb
+- lib/coradoc/markdown/serializer/strategies/admonition/container.rb
+- lib/coradoc/markdown/serializer/strategies/admonition/gfm_alert.rb
+- lib/coradoc/markdown/serializer/strategies/admonition/github.rb
+- lib/coradoc/markdown/serializer/strategies/admonition/html.rb
+- lib/coradoc/markdown/serializer/strategies/admonition/registry.rb
+- lib/coradoc/markdown/serializer/strategies/autolink/angle.rb
+- lib/coradoc/markdown/serializer/strategies/autolink/bare.rb
+- lib/coradoc/markdown/serializer/strategies/autolink/base.rb
+- lib/coradoc/markdown/serializer/strategies/autolink/none.rb
+- lib/coradoc/markdown/serializer/strategies/autolink/registry.rb
+- lib/coradoc/markdown/serializer/strategies/definition_list/base.rb
+- lib/coradoc/markdown/serializer/strategies/definition_list/flat.rb
+- lib/coradoc/markdown/serializer/strategies/definition_list/nested_html.rb
+- lib/coradoc/markdown/serializer/strategies/definition_list/registry.rb
 - lib/coradoc/markdown/toc_generator.rb
+- lib/coradoc/markdown/transform/block_transformer.rb
 - lib/coradoc/markdown/transform/from_core_model.rb
+- lib/coradoc/markdown/transform/image_transformer.rb
+- lib/coradoc/markdown/transform/inline_transformer.rb
+- lib/coradoc/markdown/transform/list_transformer.rb
+- lib/coradoc/markdown/transform/structural_transformer.rb
+- lib/coradoc/markdown/transform/table_transformer.rb
 - lib/coradoc/markdown/transform/text_extraction.rb
 - lib/coradoc/markdown/transform/to_core_model.rb
 - lib/coradoc/markdown/transformer.rb
@@ -160,7 +239,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 3.1.0
+      version: 3.3.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="